Problem
Music discovery tools often rely on genre, artist similarity, or metadata. This project explored how listeners could navigate music through emotional proximity and perceptual qualities instead.
Role
Interaction designer, product collaborator, and classification interface contributor.
Scope
RTP mood clustering, perceptual navigation, playlist workflows, prototype interfaces, and research translation.
Interaction Model
Users explored relationships between tracks through rhythm, texture, and pitch fields instead of genre hierarchies.
Outcome
A set of prototype interfaces and research-backed concepts for browsing music collections through machine-classified acoustic and emotional qualities.
Tools
Figma, research systems, acoustic classification models.
Research Context
This work contributed to interaction prototypes built around rhythm, texture, and pitch acoustic classification systems for perceptual music navigation and playlist generation.
I am listed as an inventor on related patents describing classification-driven music organization systems that cluster tracks using computed acoustic attributes rather than genre labels.
Related patents include:
Music selection and organization using rhythm, texture and pitch
Music streaming, playlist creation and streaming architecture
Music selection and organization using audio fingerprints
Research Model
Research artifacts showing rhythm, texture, pitch, and perceptual clusters for music navigation.
Early Prototype Interface Slideshow
Slideshow of early prototype screens for translating the classification model into product behavior.
Playlist and Mood Controls
Mobile interface studies for creating playlists, adjusting mood filters, and browsing RTP mood clusters.
MoodMap Calibration Study
To make the classification model more legible, I explored a calibration interface where users could adjust emotional axes, preview mood-state distributions, and navigate emotional clusters through spatial coordinates.
Resume and project walkthrough available on request.